Open‑source framework for building voice‑first and multimodal conversational AI

Pipecat is an open‑source framework that accelerates the development of voice and multimodal conversational AI applications. It offers real‑time audio processing, SDKs for speech‑to‑text, text‑to‑speech, and media handling, plus seamless integration with Daily video APIs. Backed by an active community and comprehensive docs, Pipecat lets developers create scalable, low‑latency AI assistants for web, mobile, and desktop platforms.